A Short Survey on Taxonomy Learning from Text Corpora: Issues, Resources and Recent Advances

A taxonomy is a semantic hierarchy, consisting of concepts linked by is-a relations. While a large number of taxonomies have been constructed from human-compiled resources (e.g., Wikipedia), learning taxonomies from text corpora has received a growing interest and is essential for long-tailed and domain-specific knowledge acquisition. In this paper, we overview recent advances on taxonomy construction from free texts, reorganizing relevant subtasks into a complete framework. We also overview resources for evaluation and discuss challenges for future research.

[1]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[2]  Horacio Saggion,et al.  ExTaSem! Extending, Taxonomizing and Semantifying Domain Terminologies , 2016, AAAI.

[3]  Grace Hui Yang,et al.  Constructing Task-Specific Taxonomies for Document Collection Browsing , 2012, EMNLP.

[4]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[5]  Jan Muntermann,et al.  A method for taxonomy development and its application in information systems , 2013, Eur. J. Inf. Syst..

[6]  Stefano Faralli,et al.  A Graph-Based Algorithm for Inducing Lexical Taxonomies from Scratch , 2011, IJCAI.

[7]  Deriving Boolean structures from distributional vectors , 2015, Transactions of the Association for Computational Linguistics.

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  Flavius Frasincar,et al.  Automated product taxonomy mapping in an e-commerce environment , 2015, Expert Syst. Appl..

[10]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[11]  See-Kiong Ng,et al.  Taxonomy Construction Using Syntactic Contextual Evidence , 2014, EMNLP.

[12]  Paul Buitelaar,et al.  SemEval-2015 Task 17: Taxonomy Extraction Evaluation (TExEval) , 2015, SemEval@NAACL-HLT.

[13]  Simone Paolo Ponzetto,et al.  BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network , 2012, Artif. Intell..

[14]  Roberto Navigli,et al.  Large-Scale Information Extraction from Textual Definitions through Deep Syntactic and Semantic Analysis , 2015, TACL.

[15]  Alessandro Lenci,et al.  Identifying hypernyms in distributional semantic spaces , 2012, *SEMEVAL.

[16]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[17]  Gregory Grefenstette,et al.  INRIASAC: Simple Hypernym Extraction Methods , 2015, *SEMEVAL.

[18]  Marti A. Hearst.  Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[19]  Gerhard Weikum,et al.  PATTY: A Taxonomy of Relational Patterns with Semantic Types , 2012, EMNLP.

[20]  Seung-won Hwang,et al.  Graph-Based Wrong IsA Relation Detection in a Large-Scale Lexical Taxonomy , 2017, AAAI.

[21]  Hinrich Schütze,et al.  Part-of-Speech Induction From Scratch , 1993, ACL.

[22]  Aoying Zhou,et al.  Transductive Non-linear Learning for Chinese Hypernym Prediction , 2017, ACL.

[23]  José Camacho-Collados.  Why we have switched from building full-fledged taxonomies to simply detecting hypernymy relations , 2017, ArXiv.

[24]  Daniel Jurafsky,et al.  Semantic Taxonomy Induction from Heterogenous Evidence , 2006, ACL.

[25]  Zornitsa Kozareva,et al.  A Semi-Supervised Method to Learn and Construct Taxonomies Using the Web , 2010, EMNLP.

[26]  Simone Paolo Ponzetto,et al.  Large-Scale Taxonomy Mapping for Restructuring and Integrating Wikipedia , 2009, IJCAI.

[27]  Tat-Seng Chua,et al.  Topic hierarchy construction for the organization of multi-source user generated contents , 2013, SIGIR.

[28]  Paola Velardi,et al.  Learning Word-Class Lattices for Definition and Hypernym Extraction , 2010, ACL.

[29]  Haixun Wang,et al.  Automatic Taxonomy Construction from Keywords via Scalable Bayesian Rose Trees , 2015, IEEE Transactions on Knowledge and Data Engineering.

[30]  Tomoya Takatani,et al.  Distributional Hypernym Generation by Jointly Learning Clusters and Projections , 2016, COLING.

[31]  Ido Dagan,et al.  The Distributional Inclusion Hypotheses and Lexical Entailment , 2005, ACL.

[32]  Dekang Lin,et al.  An Information-Theoretic Definition of Similarity , 1998, ICML.

[33]  Christian Biemann,et al.  Negative Sampling Improves Hypernymy Extraction Based on Projection Learning , 2017, EACL.

[34]  Ellen Riloff,et al.  Semantic Class Learning from the Web with Hyponym Pattern Linkage Graphs , 2008, ACL.

[35]  Ido Dagan,et al.  The Roles of Path-based and Distributional Information in Recognizing Lexical Semantic Relations , 2016, ArXiv.

[36]  Qinghua Zheng,et al.  Motif-Based Hyponym Relation Extraction from Wikipedia Hyperlinks , 2014, IEEE Transactions on Knowledge and Data Engineering.

[37]  Lei Zou,et al.  Efficiently Answering Technical Questions - A Knowledge Graph Approach , 2017, AAAI.

[38]  Estevam R. Hruschka,et al.  Coupled semi-supervised learning for information extraction , 2010, WSDM '10.

[39]  Haixun Wang,et al.  Understand Short Texts by Harvesting and Analyzing Semantic Knowledge , 2017, IEEE Transactions on Knowledge and Data Engineering.

[40]  Zhiting Hu,et al.  Joint Embedding of Hierarchical Categories and Entities for Concept Categorization and Dataless Classification , 2016, COLING.

[41]  Gemma Boleda,et al.  Inclusive yet Selective: Supervised Distributional Hypernymy Detection , 2014, COLING.

[42]  Katrin Erk,et al.  Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment , 2016, EMNLP.

[43]  Horacio Saggion,et al.  Supervised Distributional Hypernym Discovery via Domain Adaptation , 2016, EMNLP.

[44]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[45]  Mirella Lapata,et al.  Constructing Semantic Space Models from Parsed Corpora , 2003, ACL.

[46]  Ted Briscoe,et al.  Looking for Hyponyms in Vector Space , 2014, CoNLL.

[47]  Ignacio Iacobacci,et al.  SensEmbed: Learning Sense Embeddings for Word and Relational Similarity , 2015, ACL.

[48]  David J. Weir,et al.  Characterising Measures of Lexical Distributional Similarity , 2004, COLING.

[49]  Tiziano Flati,et al.  MultiWiBi: The multilingual Wikipedia bitaxonomy project , 2016, Artif. Intell..

[50]  Thiago Alexandre Salgueiro Pardo,et al.  A Machine Learning Approach to Automatic Term Extraction using a Rich Feature Set , 2013, HLT-NAACL.

[51]  Omer Levy,et al.  Do Supervised Distributional Methods Really Learn Lexical Inference Relations? , 2015, NAACL.

[52]  Anand Rajaraman,et al.  Building, maintaining, and using knowledge bases: a report from the trenches , 2013, SIGMOD '13.

[53]  Haixun Wang,et al.  Learning Term Embeddings for Hypernymy Identification , 2015, IJCAI.

[54]  Wei Zhang,et al.  Knowledge vault: a web-scale approach to probabilistic knowledge fusion , 2014, KDD.

[55]  Masaki Murata,et al.  Hypernym Discovery Based on Distributional Similarity and Hierarchical Structures , 2009, EMNLP.

[56]  Omer Levy,et al.  Focused Entailment Graphs for Open IE Propositions , 2014, CoNLL.

[57]  Jesse Davis,et al.  Unsupervised Learning of an IS-A Taxonomy from a Limited Domain-Specific Corpus , 2015, IJCAI.

[58]  Saif Mohammad,et al.  SemEval-2012 Task 2: Measuring Degrees of Relational Similarity , 2012, *SEMEVAL.

[59]  Masaru Kitsuregawa,et al.  Using Hidden Markov Random Fields to Combine Distributional and Pattern-Based Word Clustering , 2008, COLING.

[60]  Siu Cheung Hui,et al.  Utilizing Temporal Information for Taxonomy Construction , 2016, TACL.

[61]  Ido Dagan,et al.  Integrating Pattern-Based and Distributional Similarity Methods for Lexical Entailment Acquisition , 2006, ACL.

[62]  Ting Liu,et al.  Exploiting Multiple Sources for Open-Domain Hypernym Discovery , 2013, EMNLP.

[63]  Alessandro Lenci,et al.  How we BLESSed distributional semantic evaluation , 2011, GEMS.

[64]  Yi Zhang,et al.  On the Transitivity of Hypernym-Hyponym Relations in Data-Driven Lexical Taxonomies , 2017, AAAI.

[65]  Flavius Frasincar,et al.  Domain taxonomy learning from text: The subsumption method versus hierarchical clustering , 2013, Data Knowl. Eng..

[66]  Laura Rimell,et al.  Distributional Lexical Entailment by Topic Coherence , 2014, EACL.

[67]  Stefan Evert,et al.  The Statistics of Word Cooccur-rences: Word Pairs and Collocations , 2004 .

[68]  Gabriella Pasi,et al.  Short-text domain specific key terms/phrases extraction using an n-gram model with wikipedia , 2012, CIKM.

[69]  Wanxiang Che,et al.  Learning Semantic Hierarchies via Word Embeddings , 2014, ACL.

[70]  Doug Downey,et al.  Web-scale information extraction in knowitall: (preliminary results) , 2004, WWW '04.

[71]  Ming Gao,et al.  User Generated Content Oriented Chinese Taxonomy Construction , 2015, APWeb.

[72]  Qin Lu,et al.  Chasing Hypernyms in Vector Spaces with Entropy , 2014, EACL.

[73]  Paramita Mirza,et al.  On the contribution of word embeddings to temporal relation classification , 2016, COLING.

[74]  Koray Kavukcuoglu,et al.  Learning word embeddings efficiently with noise-contrastive estimation , 2013, NIPS.

[75]  Jiawei Han,et al.  Mining Quality Phrases from Massive Text Corpora , 2015, SIGMOD Conference.

[76]  Chengyu Wang,et al.  Chinese Hypernym-Hyponym Extraction from User Generated Categories , 2016, COLING.

[77]  Damian Smedley,et al.  The Human Phenotype Ontology project: linking molecular biology and disease through phenotype data , 2014, Nucleic Acids Res..

[78]  Ming Gao,et al.  Challenges in Chinese knowledge graph construction , 2015, 2015 31st IEEE International Conference on Data Engineering Workshops.

[79]  Dan Klein,et al.  Structured Learning for Taxonomy Induction with Belief Propagation , 2014, ACL.

[80]  Raffaella Bernardi,et al.  Entailment above the word level in distributional semantics , 2012, EACL.

[81]  Fabian M. Suchanek,et al.  YAGO3: A Knowledge Base from Multilingual Wikipedias , 2015, CIDR.

[82]  Ido Dagan,et al.  Articles: Bootstrapping Distributional Feature Vector Quality , 2009, CL.

[83]  Paul Buitelaar,et al.  SemEval-2016 Task 13: Taxonomy Extraction Evaluation (TExEval-2) , 2016, *SEMEVAL.

[84]  Wei Shen,et al.  A graph-based approach for ontology population with named entities , 2012, CIKM '12.

[85]  Amit Gupta,et al.  Revisiting Taxonomy Induction over Wikipedia , 2016, COLING.

[86]  Paul Buitelaar,et al.  Multilingual Evidence Improves Clustering-based Taxonomy Extraction , 2008, ECAI.

[87]  Siu Cheung Hui,et al.  Learning Term Embeddings for Taxonomic Relation Identification Using Dynamic Weighting Neural Network , 2016, EMNLP.

[88]  Daoud Clarke.  Context-theoretic Semantics for Natural Language: an Overview , 2009 .

[89]  Alessandro Lenci,et al.  Distributional Memory: A General Framework for Corpus-Based Semantics , 2010, CL.

[90]  Ido Dagan,et al.  Directional distributional similarity for lexical inference , 2010, Natural Language Engineering.

[91]  Tiziano Flati,et al.  Two Is Bigger (and Better) Than One: the Wikipedia Bitaxonomy Project , 2014, ACL.

[92]  Alexander J. Smola,et al.  Taxonomy discovery for personalized recommendation , 2014, WSDM.

[93]  Haixun Wang,et al.  Probase: a probabilistic taxonomy for text understanding , 2012, SIGMOD Conference.

[94]  Saif Mohammad,et al.  Experiments with three approaches to recognizing lexical entailment , 2014, Natural Language Engineering.

[95]  Dominik Schlechtweg,et al.  Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection , 2016, EACL.

[96]  Stefano Faralli,et al.  TAXI at SemEval-2016 Task 13: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling , 2016, *SEMEVAL.

[97]  Stefano Faralli,et al.  OntoLearn Reloaded: A Graph-Based Algorithm for Taxonomy Induction , 2013, CL.

[98]  Paola Velardi,et al.  Learning Domain Ontologies from Document Warehouses and Dedicated Web Sites , 2004, CL.

[99]  Flavius Frasincar,et al.  A semantic approach for extracting domain taxonomies from text , 2014, Decis. Support Syst..

[100]  Ido Dagan,et al.  Improving Hypernymy Detection with an Integrated Path-based and Distributional Method , 2016, ACL.

[101]  See-Kiong Ng,et al.  Incorporating Trustiness and Collective Synonym/Contrastive Evidence into Taxonomy Construction , 2015, EMNLP.

[102]  Josef van Genabith,et al.  USAAR-WLV: Hypernym Generation with Deep Neural Nets , 2015, *SEMEVAL.

[103]  Daniel Jurafsky,et al.  Learning Syntactic Patterns for Automatic Hypernym Discovery , 2004, NIPS.

[104]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[105]  Richard M. Karp,et al.  A simple derivation of Edmonds' algorithm for optimum branchings , 1971, Networks.

[106]  Oren Etzioni,et al.  What Is This, Anyway: Automatic Hypernym Discovery , 2009, AAAI Spring Symposium: Learning by Reading and Learning to Read.

[107]  David J. Weir,et al.  Learning to Distinguish Hypernyms and Co-Hyponyms , 2014, COLING.

[108]  Jiawei Han,et al.  Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions , 2015, IEEE Transactions on Knowledge and Data Engineering.